What is a #pytorch MCP server?
An MCP server tagged #pytorch implements the Model Context Protocol so AI assistants like Claude, Cursor, and VS Code can access pytorch-related tools, data, or APIs.
2 #pytorch MCP Servers & Clients
Every MCP server and client below is tagged #pytorch — install one to give Claude, Cursor, VS Code, or any other MCP-compatible client access to pytorch tools.
All
Ingero
ingero-io
eBPF-based GPU causal observability agent with MCP server. Traces CUDA Runtime/Driver APIs and host kernel events to build causal chains explaining GPU latency
Added 5 months ago
Forge - GPU Kernel Optimization
RightNow-AI
Turn slow PyTorch into fast CUDA/Triton kernels. 32 parallel swarm agents optimize your code on real datacenter GPUs (B200, H200, H100, A100) with up to 14x speedup over torch.compile.
Added 6 months ago
Frequently asked questions
Common questions about MCP servers and clients tagged #pytorch
How many #pytorch MCP servers and clients are there?
mcp.so currently lists 2 MCP servers and clients tagged #pytorch.
How do I install a #pytorch MCP server?
Open any server below and copy its install snippet into Claude Desktop, Cursor, VS Code, or another MCP client's configuration — remote servers need no separate download.